|Publication number||US7050964 B2|
|Application number||US 09/899,755|
|Publication date||May 23, 2006|
|Filing date||Jul 5, 2001|
|Priority date||Jun 1, 2001|
|Also published as||EP1262880A2, EP1262880A3, US7206735, US20030023422, US20060085180|
|Publication number||09899755, 899755, US 7050964 B2, US 7050964B2, US-B2-7050964, US7050964 B2, US7050964B2|
|Inventors||Arul A. Menzes, Stephen D. Richardson, Jessie E. Pinkham, William B. Dolan|
|Original Assignee||Microsoft Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (27), Non-Patent Citations (36), Referenced by (76), Classifications (8), Legal Events (4)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This application claims the benefit of U.S. provisional patent application Ser. No. 60/295,338, filed Jun. 1, 2001.
The present invention relates to automated language translation systems. More specifically, the present invention relates to a scaleable machine translation system and architecture.
Machine translation systems are systems which receive a textual input in one language, translate it to a second language, and provide a textual output in the second language. Current commercially available machine translation systems rely on hand-coded transfer components that are both difficult and expensive to customize for a particular domain, and are also very difficult to scale to a desirable size. These disadvantages have limited their cost effectiveness and overall utility.
A variety of example based machine translation systems have been created to address these deficiencies. A number of such systems are described in H. Somers, Review Article: Example—Based Machine Translation, Machine Translation 14:113,157, 1999. Some of these typical example based machine translation research systems have been built with an example base built from up to approximately 200 sentences. They have encountered a great deal of difficulty in scaling to a larger example base and the performance of the system suffers from this difficulty.
Other of the data driven systems described in Somers parse the inputs from the example base using different parsers, based upon the particular language of the input text. The dependency structures resulting from such parsing are thus different, based upon the language and the particular parsing strategy used. Therefore, comparing the dependency structures from one language to the next is difficult, if not impossible.
Such prior systems have also not been easily scalable. For example, in order to increase the number of sentences over and above, for example, 200 sentences or so, has been very difficult. This is because the prior systems have difficulty handling noisy input data. Instead, the input data has been required to be in a precise form, or it has been cleaned up, and placed in the proper form, by hand. Of course, this makes it very difficult to dramatically increase the number of sentences because of the intensive labor required to clean up the data.
A computer implemented method translates a textual input in a first language to a textual output in a second language. An input logical form is generated based on the textual input. When a plurality of transfer mappings in a transfer mapping database match the input logical form (or at least a portion thereof) one or more of those plurality of matching transfer mappings is selected based on a predetermined metric. These transfer mappings are stitched together to form a transfer Logical Form. The textual output is generated based on the transfer logical form.
A transfer mapping is illustratively composed of a pair of logical form fragments, including a source and target logical form (LF), learned from the training data. At runtime the source side of these mappings is matched against the input. Among such matched mappings, a set is chosen. The target sides of these mappings is then stitched together to produce a single target LF. The output string is then generated from the target LF.
The predetermined metric can take one of a variety of forms, including the number of input nodes covered by the set of mappings collectively, size of the different transfer mappings that match the input logical form, the frequency with which the plurality of matching transfer mappings were generated during a training phase used in training the transfer mapping database, frequencies with which the plurality of matching transfer mappings are generated from completely aligned logical forms during training, frequencies with which the plurality of matching transfer mappings were generated from non-fitted parses of the training data, and a score associated with each of the plurality of matching transfer mappings that is indicative of a confidence in the transfer mapping with which it is associated.
The present invention can also be embodied as a machine translation system including a matching component configured to implement the method discussed above.
The present invention can also be implemented as a machine translation system that includes an input generator generating an input dependency structure based on the textual input. The system also includes a transfer mapping database that holds a plurality of transfer mapping dependency structures formed based on at least 10,000 parallel, aligned, training sentences. The transfer mapping database can also be formed based on 50,000, 100,000, 180,000, or even in excess of 200,000 training sentences.
In addition, the present invention can be embodied as a computer implemented method of training a transfer mapping database which includes generating shared input logical forms for bilingual input sentences, the input logical forms being shared across both languages.
In yet another embodiment, the present invention trains the transfer mapping database by filtering transfer mappings obtained from aligned logical forms, aligned during training.
The following is a brief description of a general purpose computer 120 illustrated in
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, modules, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices. Tasks performed by the programs and modules are described below and with the aid of figures. Those skilled in the art can implement the description and figures as processor executable instructions, which can be written on any form of a computer readable media.
With reference to
Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, FR, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer readable media.
The system memory 150 includes computer storage media in the form of volatile and/or nonvolatile memory such as read only memory (ROM) 151 and random access memory (RAM) 152. A basic input/output system 153 (BIOS), containing the basic routines that help to transfer information between elements within computer 120, such as during start-up, is typically stored in ROM 151. RAM 152 typically contains data and/or program modules that are immediately accessible to and/or presently being operated on by processing unit 140. By way of example, and not limitation,
The computer 120 may also include other removable/non-removable volatile/nonvolatile computer storage media. By way of example only,
The drives and their associated computer storage media discussed above and illustrated in
A user may enter commands and information into the computer 120 through input devices such as a keyboard 182, a microphone 183, and a pointing device 181, such as a mouse, trackball or touch pad. Other input devices (not shown) may include a joystick, game pad, satellite dish, scanner, or the like. These and other input devices are often connected to the processing unit 140 through a user input interface 180 that is coupled to the system bus, but may be connected by other interface and bus structures, such as a parallel port, game port or a universal serial bus (USB). A monitor 184 or other type of display device is also connected to the system bus 141 via an interface, such as a video interface 185. In addition to the monitor, computers may also include other peripheral output devices such as speakers 187 and printer 186, which may be connected through an output peripheral interface 188.
The computer 120 may operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 194. The remote computer 194 may be a personal computer, a hand-held device, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to the computer 120. The logical connections depicted in
When used in a LAN networking environment, the computer 120 is connected to the LAN 191 through a network interface or adapter 190. When used in a WAN networking environment, the computer 120 typically includes a modem 192 or other means for establishing communications over the WAN 193, such as the Internet. The modem 192, which may be internal or external, may be connected to the system bus 141 via the user input interface 180, or other appropriate mechanism. In a networked environment, program modules depicted relative to the computer 120, or portions thereof, may be stored in the remote memory storage device. By way of example, and not limitation,
The invention is also operational with numerous other general purpose or special purpose computing systems, environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable for use with the invention include, but are not limited to, regular telephones (without any screen) personal computers, server computers, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
Prior to discussing the present invention in greater detail, a brief discussion of a logical form may be helpful. A full and detailed discussion of logical forms and systems and methods for generating them can be found in U.S. Pat. No. 5,966,686 to Heidorn et al., issued Oct. 12, 1999 and entitled METHOD AND SYSTEM FOR COMPUTING SEMANTIC LOGICAL FORMS FROM SYNTAX TREES. Briefly, however, logical forms are generated by performing a morphological analysis on an input text to produce conventional phrase structure analyses augmented with grammatical relations. Syntactic analyses undergo further processing in order to derive logical forms, which are data structures that describe labeled dependencies among content words in the textual input. Logical forms can normalize certain syntactical alternations, (e.g., active/passive) and resolve both intrasentential anaphora and long distance dependencies. As illustrated herein, for example in
Specifically, a logical relation consists of two words joined by a directional relation type, such as: LogicalSubject, LogicalObject,
A logical form is a data structure of connected logical relations representing a single textual input, such as a sentence or part thereof. The logical form minimally consists of one logical relation and portrays structural relationships (i.e., syntactic and semantic relationships), particularly argument and/or adjunct relation(s) between important words in an input string.
In one illustrative embodiment, the particular code that builds logical forms from syntactic analyses is shared across the various source and target languages that the machine translation system operates on. The shared architecture greatly simplifies the task of aligning logical form segments from different languages since superficially distinct constructions in two languages frequently collapse onto similar or identical logical form representations. Examples of logical forms in different languages are described in greater detail below with respect to
In one illustrative embodiment, a bilingual corpus is used to train the system. The bilingual corpus includes aligned translated sentences (e.g., sentences in a source or target language, such as English, in 1-to-1 correspondence with their human-created translations in the other of the source or target language, such as Spanish). During training, sentences are provided from the aligned bilingual corpus into system 200 as source sentences 230 (the sentences to be translated), and as target sentences 232 (the translation of the source sentences). Parsing components 204 and 206 parse the sentences from the aligned bilingual corpus to produce source logical forms 234 and target logical forms 236.
During parsing, the words in the sentences are converted to normalized word forms (lemmas) and can be provided to statistical word association learning component 208. Both single word and multi-word associations are iteratively hypothesized and scored by learning component 208 until a reliable set of each is obtained. Statistical word association learning component 208 outputs learned single word translation pairs 238 as well as multi-word pairs 240.
The multi-word pairs 240 are provided to a dictionary merge component 216, which is used to add additional entries into bilingual dictionary 214 to form updated bilingual dictionary 220. The new entries are representative of the multi-word pairs 240.
The single and multi-word pairs 238, along with source logical forms 234 and target logical forms 236 are provided to logical form alignment component 210. Briefly, component 210 first establishes tentative correspondences between nodes in the source and target logical forms 230 and 236, respectively. This is done using translation pairs from a bilingual lexicon (e.g. bilingual dictionary) 214, which can be augmented with the single and multi-word translation pairs 238, 240 from statistical word association learning component 208. After establishing possible correspondences, alignment component 210 aligns logical form nodes according to both lexical and structural considerations and creates word and/or logical form transfer mappings 242. This aspect will be explained in greater detail below.
Basically, alignment component 210 draws links between logical forms using the bilingual dictionary information 214 and single and multi-word pairs 238, 240. The transfer mappings are optionally filtered based on a frequency with which they are found in the source and target logical forms 234 and 236 and are provided to a lexical knowledge base building component 212.
While filtering is optional, in one example, if the transfer mapping is not seen at least twice in the training data, it is not used to build transfer mapping database 218, although any other desired frequency can be used as a filter as well. It should also be noted that other filtering techniques can be used as well, other than frequency of appearance. For example, transfer mappings can be filtered based upon whether they are formed from complete parses of the input sentences and based upon whether the logical forms used to create the transfer mappings are completely aligned.
Component 212 builds transfer mapping database 218, which contains transfer mappings that basically link words and/or logical forms in one language, to words and/or logical forms in the second language. With transfer mapping database 218 thus created, system 200 is now configured for runtime translations.
During translation run time, a source sentence 250, to be translated, is provided to analysis component 222. Analysis component 222 receives source sentence 250 and creates a source logical form 252 based upon the source sentence input. An example may be helpful. In the present example, source sentence 250 is a Spanish sentence “Haga click en el boton de opcion” which is translated into English as “Click the option button” or, literally, “Make click in the button of option”.
After a set of matching transfer mappings is found, matching component 224 creates links on nodes in the source logical form 252 to copies of the corresponding target words or logical form segments received by the transfer mappings, to generate linked logical form 254.
Transfer component 226 receives linked logical form 254 from matching component 224 and creates a target logical form 256 that will form the basis of the target translation. This is done by performing a top down traversal of the linked logical form 254 in which the target logical form segments pointed to by links on the source logical form 252 nodes are combined. When combining together logical form segments for possibly complex multi-word mappings, the sublinks set by matching component 224 between individual nodes are used to determine correct attachment points for modifiers, etc. Default attachment points are used if needed.
In cases where no applicable transfer mappings are found, the nodes in source logical form 252 and their relations are simply copied into the target logical form 256. Default single word translations may still be found in transfer mapping database 218 for these nodes and inserted in target logical form 256. However, if none are found, translations can illustratively be obtained from updated bilingual dictionary 220, which was used during alignment.
Generation component 228 is illustratively a rule-based, application-independent generation component that maps from target logical form 256 to the target string (or output target sentence) 258. Generation component 228 may illustratively have no information regarding the source language of the input logical forms, and works exclusively with information passed to it by transfer component 226. Generation component 228 also illustratively uses this information in conjunction with a monolingual (e.g., for the target language) dictionary to produce target sentence 258. One generic generation component 228 is thus sufficient for each language.
It can thus be seen that the present system parses information from various languages into a shared, common, logical form so that logical forms can be matched among different languages. The system can also utilize simple filtering techniques in building the transfer mapping database to handle noisy data input. Therefore, the present system can be automatically trained using a very large number of sentence pairs. In one illustrative embodiment, the number of sentence pairs is in excess of 10,000. In another illustrative embodiment, the number of sentence pairs is greater than 50,000 to 100,000, and may be in excess of 180,000, 200,000, 350,000 or even in excess if 500,000 or 600,000 sentence pairs. Also, the number of sentence pairs can vary for different languages, and need not be limited to these numbers.
As indicated above with respect to
Component 208 receives a parallel, bilingual training corpus that is parsed into its content words. Word association scores for each pair of content words consisting of a word of language L1 that occurs in a sentence aligned in the bilingual corpus to a sentence of language L2 in which the other word occurs. A pair of words is considered “linked” in a pair of aligned sentences if one of the words is the most highly associated, of all the words in its sentence, with the other word. The occurrence of compounds is hypothesized in the training data by identifying maximal, connected sets of linked words in each pair of aligned sentences in the processed and scored training data. Whenever one of these maximal, connected sets contains more than one word in either or both of the languages, the subset of the words in that language is hypothesized as a compound. The original input text is rewritten, replacing the hypothesized compounds by single, fused tokens. The association scores are then recomputed for the compounds (which have been replaced by fused tokens) and any remaining individual words in the input text. The association scores are again recomputed, except that this time, co-occurrences are taken into account in computing the association scores only where there is no equally strong or stronger other association in a particular pair of aligned sentences in the training corpus.
Translation pairs can be identified as those word pairs or token pairs that have association scores above a threshold, after the final computation of association scores.
Similarly, component 208 can also assist in identifying translations of “captoids”, by which we mean titles, or other special phrases, all of whose words are capitalized. (Finding translations of captoids presents a special problem in languages like French or Spanish, in which convention dictates that only the first word of such an item is capitalized, so that the extent of the captoid translation is difficult to determine.) In that embodiment, compounds are first identified in a source language (such as English). This can be done by finding strings of text where the first word begins with a capital letter, and later tokens in the contiguous string do not begin with a lowercase letter. Next, compounds are hypothesized in the target text by finding words that start with a capital letter and flagging this as the possible start of a corresponding compound. The target text is then scanned from left to right flagging subsequent words that are most strongly related to words in the identified compound in the source text, while allowing up to a predetermined number (e.g., 2) contiguous non-most highly related words, so long as they are followed by a most highly related word.
The left to right scan can be continued until more than the predetermined number (e.g., more than 2) contiguous words are found that are not most highly related to words in the identified compound in the source text, or until no more most highly related words are present in the target text, or until punctuation is reached.
While the above description has been provided for component 208, it is to be noted that component 208 is optional.
Referring again to method 300 in
Bilingual dictionary 214 represents direct translations used for forming tentative correspondences. However, in order to form additional tentative correspondences, derivational morphology can also be used. For example, translations of morphological bases and derivations, and base and derived forms of translations, can also be used to form tentative correspondences in step 302. Likewise, tentative correspondences can also be formed between nodes of the logical forms wherein one of the nodes comprises more lexical elements or words than the other node. For instance, as is common, one of the nodes can comprise a single word in one of the languages, while the other node comprises at least two words in the other language. Closely related languages such as English, Spanish, etc. also have word similarity (cognates) that can be used with fuzzy logic to ascertain associations. These associations can then be used to form tentative correspondences.
At this point, it may be helpful to consider an example of logical forms to be aligned. Referring to
Referring now to step 304, the logical forms are aligned, which can include eliminating one or more of the tentative correspondences formed in step 302, and/or which can be done as a function of structural considerations of the logical forms. In one embodiment, step 304 includes aligning nodes of the logical forms as a function of a set of rules. In a further embodiment, each of the rules of the set of rules is applied to the logical forms in a selected order. In particular, the rules are ordered to create the most unambiguous alignments (“best alignments”) first, and then, if necessary, to disambiguate subsequent node alignments. It is important to note that the order that the rules are applied in is not based upon the structure of the logical forms, i.e., top-down processing or bottom-up processing but rather, to begin with the most linguistically meaningful alignments, wherever they appear in the logical form. As such, this set of rules can be considered to be applied to the nodes of each of the logical forms non-linearly as opposed to linearly based upon the structure of the logical forms. Generally, the rules are intended to be language-neutral in order that they can be universally applied to any language.
At step 332, the set of rules is applied to each of the unaligned nodes.
If all the rules of the set of rules have been applied to all the nodes at step 340, the alignment procedure is finished. It should be noted that under some situations, not all of the nodes will be aligned.
If a rule can be applied to a set of nodes of the logical forms, the nodes are identified as being aligned and removed from the set of unaligned nodes, and application of the rules continues. However, in one embodiment, it is advantageous to begin again with the rules once some rules have been applied to obtain a more linguistically meaningful alignment. Therefore, it can be desirable to again apply rules that have previously been applied. In this manner, in one embodiment, each of the rules of the set of rules is applied again starting with, for example, the first rule as indicated at step 342.
The following is an exemplary set of rules for aligning nodes of the logical forms. The set of nodes presented herein is ordered based on the strongest to weakest linguistically meaningful alignments of the nodes. As appreciated by those skilled in the art, reordering of at least some of the rules presented herein may not significantly alter the quality of alignments of the logical forms.
1. If a bi-directionally unique translation exists between a node or set of nodes in one logical form and a node or set of nodes in the other logical form, the two nodes or sets of nodes are aligned to each other. A bi-directionally unique translation exists if a node or a set of nodes of one logical form has a tentative correspondence with a node or a set of nodes in the other logical form, such that every node in the first set of nodes has a tentative correspondence with every node in the second set of nodes, and no other correspondences, and every node in the second set of nodes has a tentative correspondence with every node in the first set of nodes, and no other correspondences.
2. A pair of parent nodes, one from each logical form, having a tentative correspondence to each other, are aligned with each other if each child node of each respective parent node is already aligned to a child of the other parent node.
3. A pair of child nodes, one from each logical form, are aligned with each other if a tentative correspondence exists between them and if a parent node of each respective child node is already aligned to a corresponding parent node of the other child.
4. A pair of nodes, one from each logical form, are aligned to each other if respective parent nodes of the nodes under consideration are aligned with each other and respective child nodes are also aligned with each other.
5. A node that is a verb and an associated child node that is not a verb from one logical form are aligned to a second node that is a verb of the other logical form if the associated child node is already aligned with the second verb node, and either the second verb node has no aligned parent nodes, or the first verb node and the second verb node have child nodes aligned with each other.
6. A pair of nodes, one from each logical form, comprising the same part-of-speech, are aligned to each other, if there are no unaligned sibling nodes, and respective parent nodes are aligned, and linguistic relationships between the set of nodes under consideration and their respective parent nodes are the same.
7. A pair of nodes, one from each logical form, comprising the same part-of-speech, are aligned to each other if respective child nodes are aligned with each other and the linguistic relationship between the set of nodes under consideration and their respective child nodes are the same.
8. If an unaligned node of one of the logical forms having immediate neighbor nodes comprising respective parent nodes, if any, all aligned, and respective child nodes, if any, all aligned, and if exactly one of the immediate nodes is a non-compound word aligned to a node of the other logical form comprising a compound word, then align the unaligned node with the node comprising the compound word. Note that the immediate neighbor nodes herein comprise adjacent parent and child nodes however the existence of parent and child nodes is not required, but if they are present, they must be aligned.
9. A pair of nodes, one from each logical form, comprising pronouns, are aligned to each other if respective parent nodes are aligned with each other and neither of the nodes under consideration have unaligned siblings.
10. A pair of nodes, one from each logical form, comprising nouns are aligned to each other if respective parent nodes comprising nouns are aligned with each other and neither of the nodes under consideration have unaligned sibling nodes, and wherein a linguistic relationship between each of the nodes under consideration and their respective parent nodes comprises either a modifier relationship or a prepositional relationship.
11. A first verb node of one logical form is aligned to a second verb node of the other logical form if the first verb node has no tentative correspondences and has a single associated child verb node that is already aligned with the second verb node.
12. A first verb node and a single, respective parent node of one logical form is aligned to a second verb node of the other logical form if the first verb node has no tentative correspondences and has a single parent verb node that is already aligned with the second verb node, where the single parent verb node has no unaligned verb child nodes besides the first verb node, and the second verb node has no unaligned verb child nodes.
13. A first node comprising a pronoun of one logical form is aligned to a second node of the other logical form if a parent node of the first node is aligned with the second node and the second node has no unaligned child nodes.
14. A first verb node and a respective parent verb of one logical form is aligned to a second verb node of the other logical form if the first verb node has no tentative correspondences and the parent verb node is aligned with the second verb node and where the relationship between the first verb and the parent verb node comprise a modal relationship.
Some general classifications of the rules provided above include that one rule (rule 1) is primarily based upon the correspondences established in step 302, and in the embodiment illustrated, it is considered to be the strongest meaningful alignment since no ambiguity is present. Other rules such as rules 2, 3, 11, 12 and 14 are based on a combination of, or a lack of, tentative correspondences and the structure of the nodes under consideration and previously aligned nodes. The remaining rules rely solely on relationships between nodes under consideration and previously aligned nodes. Other general classifications that can be drawn include that the rules pertain to verbs, nouns and pronouns.
Referring back to the logical forms and tentative correspondences of
Applying the alignment rules as described above, the alignment mappings created by the rules are illustrated in
Iterating through the rules again, rule 1 applies in three places, creating alignment mappings between “dirección” and “address”, “usted” and “you”, and “clic” and “click”. These are the initial “best” alignments that provide the anchors from which the method will work outwards to align the rest of the structure.
Rule 2 does not apply to any nodes, but Rule 3 applies next to align the instance of “hipervinculo”, that is the child of “dirección” to “hyperlink”, which is the child of “address”. The alignment method thus leveraged a previously created alignment (“dirección” to “address”) and the structure of the logical form to resolve the ambiguity present at the lexical level.
Rule 1 applies (where previously it did not) to create a many-to-one mapping between “Información” and “hipervinculo” to “Hyperlink_Information”. The uniqueness condition in this rule is now met because the ambiguous alternative was cleared away by the prior application of Rule 3.
Rule 4 does not apply, but rule 5 applies to rollup “hacer” with its object “clic”, since the latter is already aligned to a verb. This produces the many-to-one alignment of “hacer” and “clic” to “click”
Referring back to
Each mapping created during the alignment procedure can be a base structure upon which further mappings with additional context are also created. In particular, information can be stored on a computer readable medium to translate text from a first language to a second language, where the information comprises a plurality of mappings. Each mapping is indicative of associating a word or logical form of the first language with a word or logical form of the second language. However, in addition, at least some of the mappings corresponding to logical forms of the first language have varying context with some common elements. Likewise, at least some of the logical forms of the second language corresponding to the logical forms of the first language may also have varying context with some common elements. In other words, at least some of the core mappings obtained from the alignment procedure are used to create other, competing mappings having varying types and amounts of local context.
By storing mappings indicative of logical forms with overlapping context, during translation run time, fluency and general applicability of the mappings for translating between the languages is maintained. In particular, by having mappings associating both words and smaller logical forms of the languages, translation from the first language to the second language is possible if the text to be translated was not seen in the training data. However, to the extent that the larger context was present in the training data, this is also reflected in the mappings such that when a mapping of larger context is applicable, a more fluent translation between the first language and the second language can be obtained.
Generally, linguistic constructs are used to provide boundaries for expanding the core mappings to include additional context. For example, a mapping for an adjective can be expanded to include the noun it modifies. Likewise, a mapping for a verb can be expanded to include the object as context. In another example, mappings for noun collocations are provided individually as well as a whole. As further illustrated in
In general, mappings that can be created may have any number of wild-card or underspecified nodes, which may be underspecified in a number of different ways. For example, they may or may not specify a part-of-speech, and they may specify certain syntactic or semantic features. For example, a pattern may have a wild-card node with the feature “ProperName” or “Location” marked, indicating that the pattern only applies when that node is matched to an input node that has the same feature. These wild-cards allow the system to hypothesize generalized mappings from specific data.
In addition to the information pertaining to the mappings between the words or logical forms of the first language and the second language, additional information can also be stored or used during run time translation. The additional information can be used to choose an appropriate set of mappings and resolve conflicts as to which mappings to use, i.e. (referring to
For example, when the source logical form matches the source side of multiple transfer mappings in database 218, a subset of these matching transfer mappings is illustratively selected such that all transfer mappings in the subset are compatible with one another (i.e., they are not conflicting) and based on a metric that is a function of how much of the input sentence the transfer mappings in the subset collectively cover, as well as other measures related to individual transfer mappings. Some such measures are set out in Table 1.
Size of transfer mapping matched.
The frequency with which the transfer
mapping was seen in the training data.
The frequency with which the transfer
mapping was generated from fully aligned
The frequency with which the transfer
mapping was generated from partially
aligned logical forms.
The frequency with which the transfer
mapping was generated from logical forms
that resulted from a fitted parse.
An alignment score assigned to the
transfer mapping by the alignment
Once the subset of matching transfer mappings is selected, the transfer mappings in the subset are combined into a transfer logical form from which the output text is generated.
It should be noted that the subset of matching transfer mappings can contain overlapping transfer mappings, so long as they are compatible. For example, the following logical form can be generated for the Spanish sentence “Haga clic en el direccion de la oficina” which can be translated as “Click the office address”:
An example of conflicting, matching transfer mappings is shown as transfer mapping 353, which conflicts with transfer mapping 352. Therefore, for example, the logical form:
As another example of conflicting transfer mappings, assume that a number of sentences processed during training included the phrase “click <something>” that aligned to the Spanish “hacer clic en <something>”. In other sentences, assume the sentence “click <something>” aligned to “elegir <something>” (literally “select something”).
This yields the following mappings (note these examples are English mapped to Spanish whereas previous examples have been Spanish mapped to English):
for the first case, and
in the second case.
In the proper contexts, translating “click” to “select” may be a legitimate variation. However it does present a problem in some cases. For example, notice that the source side of both transfers is identical, so at runtime, if the input logical form matches that source side, we are left with having to choose between the two different target sides, i.e. it must be decided whether to translate the input as “hacer clic . . . ” or as “elegir . . . ”? In the absence of further context (which would likely have manifested itself by causing differing source sides of the transfers) we choose between them based on various frequency and scoring metrics.
Another type of conflict should also be mentioned. At runtime, for a given input sentence, there may be multiple matching transfer mappings that match different parts of the input sentence. Several of them can be chosen as the selected subset so that they can be stitched together to produce a transfer LF that covers the entire input. However, some of these matches that are stitched together will overlap one another, and some will not. Of the ones that overlap, we can only use those that are “compatible” with one another. As discussed above, by “overlap” we mean two mappings where at least one node of the input sentence is matched by both mappings. By compatible, we mean the following: matches are always compatible if they do not overlap, and matches that do overlap are compatible if the target sides that correspond to the node(s) at which they overlap are identical.
For example, if an input sentence is “cambiar configuracion de seguridad” (translated as “change the security setting”) and it matches a transfer mapping as follows:
and we match another mapping of:
then the two matches do overlap (on “configuracion”), but they are compatible, because they also both translate “configuracion” to “setting”. Therefore, we can combine them to produce a transfer LF (or target LF)of:
However suppose there was also a third mapping of:
then this mapping which does overlap the previous two at “configuracion”, is not compatible, because it would translate “configuracion” to “value”, not “setting”. Therefore, this mapping cannot be merged with the previous two, so either this transfer mapping, or the previous two, must be chosen, but not both at the same time.
Table 1 shows examples of the information that can be used to further define the subset of matching transfer mappings (either to choose among conflicting matching transfer mappings or to narrow the subset of compatible, matching transfer mappings). Such information can include how much of the input sentence is covered by the subset of matching transfer mappings (collectively) and the size of the mappings, which can be ascertained from the logical form that is matched in the transfer mapping itself. The size of a logical form includes both the number of specified nodes as well as the number of linguistic relationships between the nodes. Thus, by way of example, the size of the logical form from the source side of mapping 350 equals 2, while the size of the logical form on the target side equals 1. In another example, the logical form on the source side of mapping 354 equals 4, while the target side of mapping 354 equals 2.
The information for choosing the subset of transfer mappings can also include other information related to individual transfer mappings, such as the frequency with which the logical forms in the transfer mapping are seen in the training data. If desired, the training data can include “trusted” training data, which can be considered more reliable than other training data. The frequency of the mapping as seen in the trusted training data can be retained in addition, or in the alternative, to storing the frequency of the mapping as seen in all of the training data.
Other information that can be helpful in selecting the subset of matching transfer mappings when matching source logical forms to transfer mappings includes the extent of complete alignment of the logical forms in the training data from which the logical forms of a transfer mapping have been obtained. In other words, the alignment procedure can fully or completely align the nodes of the larger logical forms, or some nodes can remain unaligned. In the example of
Likewise, additional information can include the frequency with which the logical forms in the transfer mapping originated from a complete parse of the corresponding training data. In particular, the frequency with which the mapping originated from a complete or fitted parse, or in contrast, the frequency that the mapping originated from only a partial parse can be stored for later use in resolving conflicts while matching during translation.
Another form of information can include a score or value assigned to the transfer mapping by the alignment procedure used to extract the mapping. For instance, the score can be a function of how “strong” (linguistically meaningful) the aligned nodes are (or how confident the alignment component is in the transfer mapping). The score can therefore be a function of when (which iteration) and which rule formed the alignment. The particular function or metric used to calculate the alignment score is not crucial, and any such metric can be used to generate information related to an alignment score that can be used during run time translation.
It should be noted that, although the present invention is described above primarily with respect to analyzing, aligning and using logical forms, at least some of the inventive concepts discussed herein are applicable to other dependency structures as well.
Although the present invention has been described with reference to particular embodiments, workers skilled in the art will recognize that changes may be made in form and detail without departing from the spirit and scope of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US4839853||Sep 15, 1988||Jun 13, 1989||Bell Communications Research, Inc.||Computer information retrieval using latent semantic structure|
|US5237502 *||Aug 26, 1991||Aug 17, 1993||International Business Machines Corporation||Method and apparatus for paraphrasing information contained in logical forms|
|US5278980||Aug 16, 1991||Jan 11, 1994||Xerox Corporation||Iterative technique for phrase query formation and an information retrieval system employing same|
|US5325298||Sep 3, 1991||Jun 28, 1994||Hnc, Inc.||Methods for generating or revising context vectors for a plurality of word stems|
|US5377103||May 15, 1992||Dec 27, 1994||International Business Machines Corporation||Constrained natural language interface for a computer that employs a browse function|
|US5424947||Jun 12, 1991||Jun 13, 1995||International Business Machines Corporation||Natural language analyzing apparatus and method, and construction of a knowledge base for natural language analysis|
|US5592661||Jul 16, 1992||Jan 7, 1997||International Business Machines Corporation||Detection of independent changes via change identifiers in a versioned database management system|
|US5619709||Nov 21, 1995||Apr 8, 1997||Hnc, Inc.||System and method of context vector generation and retrieval|
|US5675745||Feb 8, 1996||Oct 7, 1997||Fujitsu Limited||Constructing method of organization activity database, analysis sheet used therein, and organization activity management system|
|US5675819||Jun 16, 1994||Oct 7, 1997||Xerox Corporation||Document information retrieval using global word co-occurrence patterns|
|US5724594||Feb 10, 1994||Mar 3, 1998||Microsoft Corporation||Method and system for automatically identifying morphological information from a machine-readable dictionary|
|US5794050||Oct 2, 1997||Aug 11, 1998||Intelligent Text Processing, Inc.||Natural language understanding system|
|US5794178||Apr 12, 1996||Aug 11, 1998||Hnc Software, Inc.||Visualization of information using graphical representations of context vector based relationships and attributes|
|US5799308||Oct 4, 1994||Aug 25, 1998||Dixon; Robert||Method and apparatus for data storage and retrieval|
|US5873056||Oct 12, 1993||Feb 16, 1999||The Syracuse University||Natural language processing system for semantic vector representation which accounts for lexical ambiguity|
|US5884247 *||Oct 31, 1996||Mar 16, 1999||Dialect Corporation||Method and apparatus for automated language translation|
|US5933833||Oct 3, 1996||Aug 3, 1999||International Business Machines Corp.||Data table structure and calculation method for mathematical calculations of irregular cells|
|US6006221||Aug 14, 1996||Dec 21, 1999||Syracuse University||Multilingual document retrieval system and method using semantic vector matching|
|US6076051||Mar 7, 1997||Jun 13, 2000||Microsoft Corporation||Information retrieval utilizing semantic representation of text|
|US6098033||Jul 31, 1997||Aug 1, 2000||Microsoft Corporation||Determining similarity between words|
|US6871174 *||May 17, 2000||Mar 22, 2005||Microsoft Corporation||System and method for matching a textual input to a lexical knowledge base and for utilizing results of that match|
|EP0304191A2||Aug 3, 1988||Feb 22, 1989||International Business Machines Corporation||Text search system|
|EP0386825A1||Feb 26, 1990||Sep 12, 1990||Bso/Buro Voor Systeemontwikkeling B.V.||Method for determining the semantic relatedness of lexical items in a text|
|EP0687987A1||Jun 14, 1995||Dec 20, 1995||Xerox Corporation||A method and apparatus for retrieving relevant documents from a corpus of documents|
|EP0805404A1||Apr 29, 1997||Nov 5, 1997||Microsoft Corporation||Method and system for lexical processing of uppercase and unaccented text|
|EP1262879A1||May 23, 2002||Dec 4, 2002||Microsoft Corporation||Automatic extraction of transfer mappings from bilingual corpora|
|EP1262880A2||May 29, 2002||Dec 4, 2002||Microsoft Corporation||Scaleable machine translation system|
|1||Agirre, Eneko, and German Rigau, "Word Sense Disambiguation Using Conceptual Density," in Proceedings of COLING 96, 1996, pp. 16-23.|
|2||Braden-Harder, Lisa, Natural Language Processing: The PLNLP Approach, Kluwer Academic Publishers, Boston, MA, 1993, Chap. 19, "Sense Disambiguation Using Online Dictionaries," pp. 247-261.|
|3||Bro'na Collins et al. Adaption-Guided Retrieval in EBMT: A Case-Based Approach to Machine Translation-1996 XP002209833 p. 91-104.|
|4||Brown et al., "Class-Based n-gram Models of Natural Language," Computational Linguistics 18(4):467-479, Dec. 1992.|
|5||Collins, B. et al. "Adaption-guided Retrieval in EBMT: a case-based approach to machine translation". EWCBR-96 Switzerland pp. 14-16.|
|6||Dagan et al., "Contextual Word Similarity and Esimation From Sparse Data," in Proceedings of the 31st Annual Meeting of the Assoc. for Computational Linguistics, Columbus, OH, Jun. 2-26, 1993, pp. 164-171.|
|7||Dagan et al., "Similarity-Based Estimation of Word Coocurrence Probabilities," in Proceedings of the 32nd Annual Meeting of the ACL, 1994, pp. 272-278.|
|8||Eesnik, Philip, "Disambiguating Noun Groups With Respect to WordNet Senses," in Proceedings of the Third Workshop on Very Large Corpora, MA, Jun. 31, 1995, pp. 1-16.|
|9||Elsbury, J.M., Personal Authentication Devices-Data Security Applications p. 471-478 1989.|
|10||Experiments in Automatic Phase Indexing for Document Retrieval: A Comparison of Syntactic and Nonsyntactic Methods, by Joel L. Fagan Degree Date: 1988.|
|11||Furuse, Osamu, and Hitoshi Iida, "An Example-Based Method for Transfer-Driven Machine Translation,"in Proc. Of the 4th International Conference on Theoretical and Methodological Issues in Machine Translation, Montreal, Quebec, Canada, 1992, pp. 139-150.|
|12||Grishman, Ralph, and John Sterling, "Generalizing Automatically Generated Selectional patterns," in Proceedings of the 15th International Conference on Computational Linguistics, Kyoto, Japan, Aug. 5-9, 1994, pp. 742-747.|
|13||Habichler, Jurgen: "Experts (EDI/XML Procurement Enabling Real Trade Standards)" May 1999. pp. 1-13.|
|14||Hearst, Marti A., and Gregory Grefenstette, Refining Automatically-Discovered Lexical Relations: Combining Weak Techniques for Stronger Results,: in Papers From the 1992 AAAI Workshop, Menlo Park, CA 1992, pp. 64-72.|
|15||Hindle, Donald, "Noun Classification From Predicate-Argument Structures," in Proceedings of the 28th Annual Meetings of the ACL, Pittsburg, PA. Jun. 6-9, 1990, pp. 268-275.|
|16||James Allen, "Natural Language Understanding" The Benjamin/Cumming Publishing Company, Inc. Semantic Forms and Logic, Chapter 8. pp. 227-260, 1995.|
|17||Kozima, Hideki, and Teiji Furugori, "Similarity Between Words Computed by Spreading Activation on an English Dictionary," in Proceedings of the 6th Conference of the European Chapter of the ACL, Utrecht, Germany, 1993, pp. 232-240.|
|18||Meyers, Adam et al., "Alignment of Shared Forests for Bilingual Corpora". p. 1-6 (1996).|
|19||Michael, Carl: "Inducing Translation Templates for Example-Based Machine Translation". Proceedings of MT-Summit VII. 1999. URL:http://www.iai.uni-sb.de/docs/edgar.pdf paragraph 03.2-last paragraph.|
|20||Oz, Z et al. "Ordering translation templates by assigning confidence factors". Machine Translation and the Information Soup. 1998 Berlin AMTA pp. 51-61.|
|21||Pereira et al., "Distributional Clustering of English Words," in Proceedings of the 31st Annual Meeting of Assoc. for Computational Linguistics, Columbus, OH, Jun. 22-26, 1993, pp. 183-190.|
|22||Resnik, Philip, "Disambiguating Noun Groupings With Respect to WordNet Sense," in Proceedings of the 3rd Workshop on Very Large Corpora, Boston, MA., Jun. 30, 1995, pp. 1-16.|
|23||Sadler, Victor, Working With Analogical Semantics: Disambiguation Techniques in DLT, Foris Publications, Dordrecht, Holland, 1989, entire book.|
|24||Salton, Gerard, and Michael J. McGill, Introduction to Modern Information Retrieval, McGraw-Hill Publishing Co., New York, NY 1983, entire book.|
|25||Salton, Gerard: "Automatic Information Organization and Retrieval", McGraw Hill Book Company, pp. 168-178, 1968.|
|26||Sato, Satoshi, "Example-Based Machine Translation," in Proceedings of the International Workshop on Fundamental Research for the Future Generation of Natural Language Processing, Kyoto, Japan, Sep. 1991, pp. 1-16.|
|27||Somers, H. "Review Article: Example-based 25 Machine Translation", vol. 14, 1999, p. 113-157.|
|28||Somers, Harold "Review Article: Example-based Machine Translation" 2001 Kluwer Academic Pub. Printed in the Netherlands p. 113-157.|
|29||Sumita, Eiichiro, and Hotioshi Iida, "Experiments and Prospects of Example-Based Machine Translation," in Proceedings of the 29th Annual Meetings of the ACL, 1991, pp. 185-192.|
|30||Tsutsumi, Taijiro, Natural Language Processing: The PLNLP Approach, Kluwer Academic Publishers, Boston, MA, 1993, Chap. 20, "Word-Sense Disambiguation by Examples," pp. 263-272.|
|31||Uramoto, Naohiko, "A Best-Match Algorithm for Broad-Coverage Example-Based Disambiguation," in Proceedings of the 15th International Conference on Computational Linguistics, Kyoto, Japan, Aug. 5-9, 1994, pp. 717-721.|
|32||Utsuro et al., "Thesaurus-Based Efficient Example Retrieval by Generating Retrieval Queries From Similarities," in Proceedings of the 15th International Conference on Computational Linguistics, Kyoto, Japan, Aug. 509, 1994, pp. 1044-1048.|
|33||Van Zuijlen, Job. M., "Probabilistic Methods in Dependency Grammar Parsing": International Parsing Workshop. 10375:142-141, 1989.|
|34||Wilks et al., "Providing Machine Tractable Dictonary Tools," Machine Translations 5:99-154, 1990.|
|35||Yarowsky, David, "Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora," in Proceedings in the 15th Int'l. Conference on Computational Linguistics, Nantes, France, Aug. 23-28, 1992, pp. 454-460.|
|36||Zeynep Oz et al. Ordering Translation Templates by Assigning Confidence Factors XP-002209835.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7206735 *||Dec 1, 2005||Apr 17, 2007||Microsoft Corporation||Scaleable machine translation|
|US7209875 *||Dec 4, 2002||Apr 24, 2007||Microsoft Corporation||System and method for machine learning a confidence metric for machine translation|
|US7493293 *||May 31, 2006||Feb 17, 2009||International Business Machines Corporation||System and method for extracting entities of interest from text using n-gram models|
|US7496496||Mar 19, 2007||Feb 24, 2009||Microsoft Corporation||System and method for machine learning a confidence metric for machine translation|
|US7546235||Nov 15, 2004||Jun 9, 2009||Microsoft Corporation||Unsupervised learning of paraphrase/translation alternations and selective application thereof|
|US7552046||Nov 15, 2004||Jun 23, 2009||Microsoft Corporation||Unsupervised learning of paraphrase/translation alternations and selective application thereof|
|US7584092||Nov 15, 2004||Sep 1, 2009||Microsoft Corporation||Unsupervised learning of paraphrase/translation alternations and selective application thereof|
|US7752034||Oct 7, 2005||Jul 6, 2010||Microsoft Corporation||Writing assistance using machine translation techniques|
|US7908132 *||Sep 29, 2005||Mar 15, 2011||Microsoft Corporation||Writing assistance using machine translation techniques|
|US8099341||Aug 24, 2006||Jan 17, 2012||OREM Financial Services Inc.||System and method for recreating tax documents|
|US8140267||Jun 30, 2006||Mar 20, 2012||International Business Machines Corporation||System and method for identifying similar molecules|
|US8145473||Mar 27, 2012||Abbyy Software Ltd.||Deep model statistics method for machine translation|
|US8195447||Mar 22, 2007||Jun 5, 2012||Abbyy Software Ltd.||Translating sentences between languages using language-independent semantic structures and ratings of syntactic constructions|
|US8209166 *||Mar 18, 2008||Jun 26, 2012||Kabushiki Kaisha Toshiba||Apparatus, method, and computer program product for machine translation|
|US8214196||Jul 3, 2002||Jul 3, 2012||University Of Southern California||Syntax-based statistical translation model|
|US8214199||Mar 22, 2007||Jul 3, 2012||Abbyy Software, Ltd.||Systems for translating sentences between languages using language-independent semantic structures and ratings of syntactic constructions|
|US8234106||Oct 8, 2009||Jul 31, 2012||University Of Southern California||Building a translation lexicon from comparable, non-parallel corpora|
|US8275605||May 4, 2010||Sep 25, 2012||Microsoft Corporation||Machine language translation with transfer mappings having varying context|
|US8380486||Oct 1, 2009||Feb 19, 2013||Language Weaver, Inc.||Providing machine-generated translations and corresponding trust levels|
|US8412513||Apr 2, 2013||Abbyy Software Ltd.||Deep model statistics method for machine translation|
|US8433556||Nov 2, 2006||Apr 30, 2013||University Of Southern California||Semi-supervised training for statistical word alignment|
|US8442810||May 14, 2013||Abbyy Software Ltd.||Deep model statistics method for machine translation|
|US8468149||Jun 18, 2013||Language Weaver, Inc.||Multi-lingual online community|
|US8489385 *||Jun 25, 2012||Jul 16, 2013||University Of Washington||Use of lexical translations for facilitating searches|
|US8548794 *||Jul 2, 2004||Oct 1, 2013||University Of Southern California||Statistical noun phrase translation|
|US8548795||Aug 6, 2008||Oct 1, 2013||Abbyy Software Ltd.||Method for translating documents from one language into another using a database of translations, a terminology dictionary, a translation dictionary, and a machine translation system|
|US8600728||Oct 12, 2005||Dec 3, 2013||University Of Southern California||Training for a text-to-text application which uses string to tree conversion for training and decoding|
|US8615389||Mar 14, 2008||Dec 24, 2013||Language Weaver, Inc.||Generation and exploitation of an approximate language model|
|US8666725||Apr 15, 2005||Mar 4, 2014||University Of Southern California||Selection and use of nonstatistical translation components in a statistical machine translation framework|
|US8676563||Jun 21, 2010||Mar 18, 2014||Language Weaver, Inc.||Providing human-generated and machine-generated trusted translations|
|US8694303||Jun 15, 2011||Apr 8, 2014||Language Weaver, Inc.||Systems and methods for tuning parameters in statistical machine translation|
|US8706477||Apr 25, 2008||Apr 22, 2014||Softwin Srl Romania||Systems and methods for lexical correspondence linguistic knowledge base creation comprising dependency trees with procedural nodes denoting execute code|
|US8762130||Jun 17, 2009||Jun 24, 2014||Softwin Srl Romania||Systems and methods for natural language processing including morphological analysis, lemmatizing, spell checking and grammar checking|
|US8762131||Jun 17, 2009||Jun 24, 2014||Softwin Srl Romania||Systems and methods for managing a complex lexicon comprising multiword expressions and multiword inflection templates|
|US8805676||Sep 25, 2012||Aug 12, 2014||Abbyy Infopoisk Llc||Deep model statistics method for machine translation|
|US8825466||Jun 8, 2007||Sep 2, 2014||Language Weaver, Inc.||Modification of annotated bilingual segment pairs in syntax-based machine translation|
|US8831928||Apr 4, 2007||Sep 9, 2014||Language Weaver, Inc.||Customizable machine translation service|
|US8886515||Oct 19, 2011||Nov 11, 2014||Language Weaver, Inc.||Systems and methods for enhancing machine translation post edit review processes|
|US8886517||Jun 29, 2012||Nov 11, 2014||Language Weaver, Inc.||Trust scoring for language translation systems|
|US8886518||Aug 7, 2006||Nov 11, 2014||Language Weaver, Inc.||System and method for capitalizing machine translated text|
|US8892418||Jul 20, 2012||Nov 18, 2014||Abbyy Infopoisk Llc||Translating sentences between languages|
|US8918309||Dec 20, 2012||Dec 23, 2014||Abbyy Infopoisk Llc||Deep model statistics method for machine translation|
|US8942973||Mar 9, 2012||Jan 27, 2015||Language Weaver, Inc.||Content page URL translation|
|US8943080 *||Dec 5, 2006||Jan 27, 2015||University Of Southern California||Systems and methods for identifying parallel documents and sentence fragments in multilingual document collections|
|US8959011||Jan 26, 2012||Feb 17, 2015||Abbyy Infopoisk Llc||Indicating and correcting errors in machine translation systems|
|US8971630||Jun 19, 2012||Mar 3, 2015||Abbyy Development Llc||Fast CJK character recognition|
|US8977536||Jun 3, 2008||Mar 10, 2015||University Of Southern California||Method and system for translating information with a higher probability of a correct translation|
|US8989485||Oct 14, 2013||Mar 24, 2015||Abbyy Development Llc||Detecting a junction in a text line of CJK characters|
|US8990064||Jul 28, 2009||Mar 24, 2015||Language Weaver, Inc.||Translating documents based on content|
|US9047275||May 4, 2012||Jun 2, 2015||Abbyy Infopoisk Llc||Methods and systems for alignment of parallel text corpora|
|US9122674||Dec 15, 2006||Sep 1, 2015||Language Weaver, Inc.||Use of annotations in statistical machine translation|
|US9152622||Nov 26, 2012||Oct 6, 2015||Language Weaver, Inc.||Personalized machine translation via online adaptation|
|US9213694||Oct 10, 2013||Dec 15, 2015||Language Weaver, Inc.||Efficient online domain adaptation|
|US9235573||Nov 8, 2012||Jan 12, 2016||Abbyy Infopoisk Llc||Universal difference measure|
|US9239826||Sep 19, 2014||Jan 19, 2016||Abbyy Infopoisk Llc||Method and system for generating new entries in natural language dictionary|
|US20050038643 *||Jul 2, 2004||Feb 17, 2005||Philipp Koehn||Statistical noun phrase translation|
|US20050102130 *||Dec 4, 2002||May 12, 2005||Quirk Christopher B.||System and method for machine learning a confidence metric for machine translation|
|US20060053001 *||Oct 7, 2005||Mar 9, 2006||Microsoft Corporation||Writing assistance using machine translation techniques|
|US20060085180 *||Dec 1, 2005||Apr 20, 2006||Microsoft Corporation||Scaleable machine translation|
|US20060106592 *||Nov 15, 2004||May 18, 2006||Microsoft Corporation||Unsupervised learning of paraphrase/ translation alternations and selective application thereof|
|US20060106594 *||Nov 15, 2004||May 18, 2006||Microsoft Corporation||Unsupervised learning of paraphrase/translation alternations and selective application thereof|
|US20060106595 *||Nov 15, 2004||May 18, 2006||Microsoft Corporation||Unsupervised learning of paraphrase/translation alternations and selective application thereof|
|US20060271451 *||Aug 24, 2006||Nov 30, 2006||George Varughese||System and method for providing data to tax preparation software|
|US20060282354 *||Aug 24, 2006||Dec 14, 2006||Dennis Varghese||System and method for recreating tax documents|
|US20070073532 *||Sep 29, 2005||Mar 29, 2007||Microsoft Corporation||Writing assistance using machine translation techniques|
|US20070219774 *||Mar 19, 2007||Sep 20, 2007||Microsoft Corporation||System and method for machine learning a confidence metric for machine translation|
|US20070250306 *||Dec 5, 2006||Oct 25, 2007||University Of Southern California||Systems and methods for identifying parallel documents and sentence fragments in multilingual document collections|
|US20080004810 *||Jun 30, 2006||Jan 3, 2008||Stephen Kane Boyer||System and Method for Identifying Similar Molecules|
|US20080040298 *||May 31, 2006||Feb 14, 2008||Tapas Kanungo||System and method for extracting entities of interest from text using n-gram models|
|US20080086298 *||Mar 22, 2007||Apr 10, 2008||Anisimovich Konstantin||Method and system for translating sentences between langauges|
|US20080086299 *||Mar 22, 2007||Apr 10, 2008||Anisimovich Konstantin||Method and system for translating sentences between languages|
|US20080086300 *||Mar 22, 2007||Apr 10, 2008||Anisimovich Konstantin||Method and system for translating sentences between languages|
|US20090012776 *||Mar 18, 2008||Jan 8, 2009||Tetsuro Chino||Apparatus, method, and computer program product for machine translation|
|US20090070099 *||Aug 6, 2008||Mar 12, 2009||Konstantin Anisimovich||Method for translating documents from one language into another using a database of translations, a terminology dictionary, a translation dictionary, and a machine translation system|
|US20100223049 *||May 4, 2010||Sep 2, 2010||Microsoft Corporation||Machine language translation with transfer mappings having varying context|
|US20120271622 *||Jun 25, 2012||Oct 25, 2012||University Of Washington||Use of lexical translations for facilitating searches|
|U.S. Classification||704/2, 704/10|
|International Classification||G06F17/21, G06F17/28|
|Cooperative Classification||G06F17/2827, G06F17/2872|
|European Classification||G06F17/28R, G06F17/28D4|
|Jan 4, 2002||AS||Assignment|
Owner name: MICROSOFT CORPORATION, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MENEZES, AURL A.;RICHARDSON, STEPHEN D.;PINKHAM, JESSIE E.;AND OTHERS;REEL/FRAME:012432/0871
Effective date: 20010927
|Oct 21, 2009||FPAY||Fee payment|
Year of fee payment: 4
|Oct 11, 2013||FPAY||Fee payment|
Year of fee payment: 8
|Dec 9, 2014||AS||Assignment|
Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034541/0001
Effective date: 20141014